Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    python function definitions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Financial
    0.42
     रण
    0.40
     Bud
    0.39
     Financial
    0.39
     financiero
    0.38
    వ్ర
    0.38
    禳
    0.38
    谕
    0.38
    뜹
    0.38
     फाइ
    0.37
    POSITIVE LOGITS
    antal
    0.41
     crystallinity
    0.41
    scht
    0.40
    olm
    0.40
    組み合わせ
    0.39
    orphous
    0.39
    Semit
    0.38
    ıt
    0.38
     étn
    0.38
     crystalline
    0.37
    Act Density 0.031%

    No Known Activations